view post Post 13263 deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️ > pretty insane it can parse and re-render charts in HTML> it uses CLIP and SAM features concatenated, so better grounding> very efficient per vision tokens/performance ratio> covers 100 languages See translation
Weekly Releases (Jun 19, 2026) Boogu/Boogu-Image-0.1-Turbo Updated about 3 hours ago • 671 • 56 datalab-to/lift Image-Text-to-Text • 10B • Updated 7 days ago • 5.19k • 152 Comfy-Org/Boogu-Image Updated about 15 hours ago • 93 Boogu/Boogu-Image-0.1-Turbo-fp8 Updated about 3 hours ago • 504 • 45
my recommended vision/mm models detection, segmentation, OCR, depth, pose, grounding, VLM detection Roboflow/rf-detr-base Object Detection • 32.2M • Updated May 20 • 1.29k • 4 Roboflow/rf-detr-seg-large Image Segmentation • 36.2M • Updated May 20 • 99 • 2 Roboflow/rf-detr-seg-medium Image Segmentation • 35.7M • Updated May 20 • 573 • 3 facebook/sam3 Mask Generation • 0.9B • Updated Nov 20, 2025 • 1.72M • 2.32k
Weekly Releases (Jun 19, 2026) Boogu/Boogu-Image-0.1-Turbo Updated about 3 hours ago • 671 • 56 datalab-to/lift Image-Text-to-Text • 10B • Updated 7 days ago • 5.19k • 152 Comfy-Org/Boogu-Image Updated about 15 hours ago • 93 Boogu/Boogu-Image-0.1-Turbo-fp8 Updated about 3 hours ago • 504 • 45
my recommended vision/mm models detection, segmentation, OCR, depth, pose, grounding, VLM detection Roboflow/rf-detr-base Object Detection • 32.2M • Updated May 20 • 1.29k • 4 Roboflow/rf-detr-seg-large Image Segmentation • 36.2M • Updated May 20 • 99 • 2 Roboflow/rf-detr-seg-medium Image Segmentation • 35.7M • Updated May 20 • 573 • 3 facebook/sam3 Mask Generation • 0.9B • Updated Nov 20, 2025 • 1.72M • 2.32k
merve/rfdetr-docvqa-media3-trainval-agree1-medium Object Detection • 33.4M • Updated 9 days ago • 543
merve/rfdetr-docvqa-media3-trainval-agree2-medium Object Detection • 33.4M • Updated 9 days ago • 395